Predictive insights: leveraging Twitter sentiments and machine learning for environmental, social and governance controversy prediction

Yasemin Lheureux ()
Additional contact information
Yasemin Lheureux: Université de Bordeaux

Journal of Computational Social Science, 2024, vol. 7, issue 1, No 2, 23-44

Abstract: Abstract This research introduces an innovative approach that utilizes machine learning to forecast Environmental, Social, and Governance (ESG) controversies within corporations, based on public opinions expressed on Twitter. Drawing on the theoretical foundations of legitimacy theory and stakeholder theory, the proposed methodology emphasizes the essential role of stakeholder engagement in effectively managing ESG risks and promoting sustainable business practices. Through the examination of eight machine-learning algorithms, the research showcases the accurate forecasting of ESG controversies, specifically achieving a remarkable overall F1-Score of 80% by LightGBM. The findings underscore the significant contribution of machine learning models and social media analytics in ESG risk management and controversy mitigation. Companies can anticipate potential controversies and proactively improve their Corporate Social Responsibility practices by actively monitoring public sentiments, especially on social media platforms. Analyzing positive sentiments as indicators of successful practices and negative sentiments as potential areas of concern further enhances their legitimacy and foster stakeholder engagement.

Keywords: Machine learning; Twitter sentiment analysis; ESG controversies; CSR; Stakeholder; Legitimacy (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42001-023-00228-5 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:jcsosc:v:7:y:2024:i:1:d:10.1007_s42001-023-00228-5

Ordering information: This journal article can be ordered from
http://www.springer. ... iences/journal/42001

DOI: 10.1007/s42001-023-00228-5

Access Statistics for this article

Journal of Computational Social Science is currently edited by Takashi Kamihigashi

More articles in Journal of Computational Social Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().